Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Helps you use Unsloth for language model fine-tuning with LoRA and QLoRA, methods that adapt models with fewer trainable parameters. Supports API questions, implementation, and debugging using reference material drawn from official documentation.
Find language models on Hugging Face Hub and run them locally with llama.cpp. The skill helps compare GGUF model files, choose compressed versions that fit available memory, and prepare commands for a local chat server or command-line session.
Build question answering and document retrieval workflows with DSPy by defining inputs, outputs, and reusable components. Use training examples and evaluation metrics to automatically optimize prompts and compare results before and after optimization.
Use the hf command-line tool to find, download, and upload models and datasets on Hugging Face Hub. The guide also covers repository management, hosted computing resources, local cache maintenance, and automation options.
Set up vLLM to serve large language models through an OpenAI-compatible API or process prompts in batches. The skill covers deployment, performance monitoring, and quantization, which reduces model memory requirements.
Guide language model training with TRL using example answers, preferred response pairs, or reward scores. The skill covers data preparation, method selection, reward model training, evaluation, and adjustments for memory limits or unstable training.
Generate model responses in defined formats for data extraction and classification. Use JSON schemas, Pydantic data models, regular expressions, or fixed choices to produce structured results that other programs can parse and validate.
Get guidance for fine-tuning large language models with Axolotl, adapting them through additional training. Use YAML configuration examples, dataset references, and training methods such as LoRA to set up training and investigate problems.
Use SAM to separate objects from images by marking points or drawing boxes, without training a model for each task. Covers automatic region generation, refining selections, preparing annotation data, and exporting models for deployment.
Set up large language model pretraining with TorchTitan and PyTorch. Configure training across multiple GPUs, combine four ways of splitting the workload, enable Float8 calculations on H100 hardware, and manage checkpoints for saving and resuming training.
Build agent memory with Pinecone by storing searchable representations of conversations and documents. Retrieve relevant past context for answers, organize memory by session or user, and prototype semantic search that finds information by meaning.
Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.
Improve prompts, regex patterns, SQL queries, or small code snippets through repeated scoring and revision. The skill helps define measurable tests, generate new candidates with an AI model, and inspect results to find better-performing versions.
Evaluate large language models on shared tests of knowledge, reasoning, and code generation with lm-evaluation-harness. Save scores and individual predictions, compare models in tables, and track performance across saved stages of model training.
Extract website content using direct HTTP requests, JavaScript-capable browsers, or stealth browsing with Cloudflare handling. Use selectors to collect specific data, crawl linked pages, and export results as Markdown, text, HTML, or JSON.
Track machine learning experiments in W&B, record training settings and metrics, and compare results in dashboards. Automate searches for training settings and keep version histories for models and datasets.
Build document search with Chroma, a database that stores text as numerical representations of meaning. Save and update documents, filter by metadata, and connect retrieval to AI applications using LangChain or LlamaIndex.
Train language models on pairs of preferred and rejected answers without a separate reference model. The skill guides training setup, model-specific configurations, parameter tuning, and troubleshooting for unstable training or memory limits.
Prepare LLM training datasets with NeMo Curator by removing duplicates, filtering low-quality content, and redacting personal information. The skill also covers image, video, and audio curation, including GPU processing and distributed workflows.
Find and run over 150 cloud AI apps through a shared command-line tool. Generate images and videos, search for information, or upload local images and audio for tasks such as upscaling and avatar generation.
Fine-tune large language models with LoRA and QLoRA, methods that train small additions to a base model while limiting GPU memory use. Configure training, save task-specific adapters, switch between them, and merge them for deployment.
Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.
Use LLaVA, a model that understands images and text, to answer questions about pictures, write image descriptions, and build image chat applications. Includes guidance for setup, ongoing conversations, and model memory options.
Integrate Flash Attention into Transformer models to speed up attention, the calculation that relates input elements, while reducing GPU memory use. Covers PyTorch integration, performance measurement, output comparison, and a separate H100 optimization path.